CN106648895A - Data processing method and device, and terminal - Google Patents
Data processing method and device, and terminal Download PDFInfo
- Publication number
- CN106648895A CN106648895A CN201611215723.9A CN201611215723A CN106648895A CN 106648895 A CN106648895 A CN 106648895A CN 201611215723 A CN201611215723 A CN 201611215723A CN 106648895 A CN106648895 A CN 106648895A
- Authority
- CN
- China
- Prior art keywords
- data
- gpu
- predetermined system
- default capabilities
- performance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5094—Allocation of resources, e.g. of the central processing unit [CPU] where the allocation takes into account power or heat criteria
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
Abstract
The invention discloses a data processing method and device, and a terminal. The method comprises the following steps: determining an operation of which a performance index exceeds a preset performance index during a preset system operating process according to a preset performance assessment model; in the preset system operating process, equally distributing data corresponding to the operation to a GPU (Graphics Processing Unit) for performing computing processing to obtain a data processing result. According to the data processing method, the data processing device and the terminal, various situations in the system operating process are simulated through the preset performance assessment model, the operation of which the performance index exceeds the preset performance index in various operations is determined on that basis, and the operation is determined to be as the operation with high load; therefore, during actual operating process of the system, once the operation is found, the data corresponding to the operation are distributed to the GPU for processing so as to share the load of a CPU (Central Processing Unit), and then the data of the terminal during a using process are shared, the situation that a system is stuck cannot be caused any longer; problems in the prior art are solved.
Description
Technical field
The present invention relates to field of mobile communication, more particularly to a kind of method of processing data, device and terminal.
Background technology
The smart mobile phone of android system is in use for some time, it will usually the problems such as system interim card occur, Er Qiesui
The increase of use time, system interim card will become apparent from, and have a strong impact on Consumer's Experience, cause customer loss.
At present manufacturer terminal is directed to system interim card, and the solution on hardware is exactly that the hardware for constantly improving mobile phone is matched somebody with somebody
Put, from operation faster, the more CPU of check figure (central processing unit, Central Processing Unit), from bigger
Internal memory, improves hardware performance to improve the computing capability of whole mobile phone, alleviates system interim card.Solution on software is exactly
Mobile phone housekeeper service is provided, allows user regularly to clear up mobile phone space, some manufacturers even monitoring cell-phone idle is idle in mobile phone
Period kills the big process of resource overhead amount on backstage silently, closes application or mobile phone is restarted automatically.Comprehensive hardware and soft
The measure of two aspects of part, the hardware for enabling mobile phone provides process of enough computing resources to being currently running.
Mobile phone terminal manufacturer in order to improve the fluency of the operational capability of mobile phone, strengthening system and application operation, constantly
Improve the computing capability of the single kernels of CPU and improve the computing capability of whole CPU using multinuclear, so as to cause the frequency of CPU core
Rate more and more higher, the check figure of CPU is more and more, thus brings a series of problem, such as frequency improve bring cell-phone heating,
The problems such as power consumption increases;Additionally, being restricted by factors such as CPU processing technologys, battery lifes, the frequency of mobile phone CPU
Rate and check figure can not be improved again after certain peak value is reached, and can otherwise be brought cell-phone heating, outward appearance to become ugly, volume and be become big
Etc. a series of bad Consumer's Experiences.
Therefore, after the frequency and check figure of CPU reach bottleneck, the computing capability of CPU is limited to, cannot be further
System interim card is solved the problems, such as, user still occurs system interim card during using terminal, experiences relatively low.
The content of the invention
The invention provides a kind of method of processing data, device and terminal, at least to solve asking as follows for prior art
Topic:After the frequency and check figure of CPU reach bottleneck, the computing capability of CPU is limited to, cannot further solve system card
Problem, user still occurs system interim card during using terminal, experiences relatively low.
On the one hand, the present invention provides a kind of method of processing data, including:Determined according to default capabilities assessment models default
Performance indications exceed the operation of default capabilities index in system operation;In the predetermined system running, will be described
Operating corresponding data to distribute to GPU (graphic process unit, Graphics Processing Unit) carries out calculating process, with
Obtain the result of the data.
Optionally, the corresponding data of the operation are distributed to into GPU process, including:By CPU by the data
View data is processed as, and is sent to the GPU, so that the GPU carries out calculating process to described image data;By CPU
The view data after the GPU calculating is processed is received, and dissection process is carried out to described image data, to obtain the data
Result.
Optionally, determine that performance indications exceed default capabilities in predetermined system running according to default capabilities assessment models
The operation of index, including:The number of executions of all operations in predetermined system running is simulated according to default capabilities assessment models,
And determine that the number of executions exceedes the operation of predetermined number;Or, simulate predetermined system fortune according to default capabilities assessment models
The Performance Score of all operations during row, and determine that the Performance Score exceedes the operation of default capabilities scoring.
Optionally, the building process of the default capabilities assessment models, including:According to each present in the predetermined system
Individual function carries out Performance Evaluation Model instantiation;Build after instantiation for the device parameter of predetermined system place equipment
Performance Evaluation Model;The Performance Evaluation Model that all structures are completed is combined, to obtain the corresponding institute of the predetermined system
State default capabilities assessment models.
Optionally, Performance Evaluation Model instantiation is carried out according to each function present in the predetermined system, including:For
Each corresponding each function setting component of operation in the predetermined system, and corresponding service equipment is set for each component;
The Performance Score and weighted value when it is corresponding service equipment service is set for each component, with according to each component
Performance Score and the weighted value determine the Performance Score of respective operations.
On the other hand, present invention also offers a kind of device of processing data, including:Determining module, for according to default
Performance Evaluation Model determines operation of the performance indications more than default capabilities index in predetermined system running;Processing module, uses
In in the predetermined system running, the corresponding data of the operation are distributed to into GPU carries out calculating process, to obtain
The result of the data.
Optionally, the processing module specifically for:By CPU by the data processing be view data, and send to
The GPU, so that the GPU carries out calculating process to described image data;Received after the GPU calculating process by CPU
View data, and dissection process is carried out to described image data, to obtain the result of the data.
Optionally, the determining module specifically for:Predetermined system running is simulated according to default capabilities assessment models
The number of executions of middle all operations, and determine that the number of executions exceedes the operation of predetermined number;Or, commented according to default capabilities
Estimate the Performance Score of all operations in modeling predetermined system running, and determine that the Performance Score exceedes default capabilities
The operation of scoring.
Optionally, described device also includes:Construction part module, it is concrete to build for building the default capabilities assessment models
Process is as follows:Performance Evaluation Model instantiation is carried out according to each function present in the predetermined system;For described default
The device parameter of system place equipment builds the Performance Evaluation Model after instantiation;By all Performance Evaluation Models for building and completing
It is combined, to obtain the corresponding default capabilities assessment models of the predetermined system.
On the other hand, present invention also offers a kind of terminal, including:The device of above-mentioned processing data.
The present invention by default capabilities assessment models come simulation system running in various situations, come on this basis
Determine each operation in performance indications exceed default capabilities index operation, this generic operation is exactly the higher operation of load, therefore,
Just the corresponding data of the operation can be carried out distributing to GPU during running, when the operation is found
Process, to share the load of CPU, and then terminal data in use are shared process, system interim card will not again occur
Situation, solve the following problem of prior art:After the frequency and check figure of CPU reach bottleneck, the calculating energy of CPU is limited to
Power, cannot further solve the problems, such as system interim card, and user still occurs system interim card during using terminal,
Experience is relatively low.
Description of the drawings
By the detailed description for reading hereafter preferred embodiment, various other advantages and benefit is common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred embodiment, and is not considered as to the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical part.In the accompanying drawings:
Fig. 1 is the flow chart of the method for processing data in first embodiment of the invention;
Fig. 2 is the flow chart of the method for processing data in second embodiment of the invention;
Fig. 3 is the structural representation of the device of processing data in sixth embodiment of the invention;
Fig. 4 is the procedure chart that the performance model in seventh embodiment of the invention based on android system component maps;
Fig. 5 is the sequential chart of interaction between component in seventh embodiment of the invention;
Fig. 6 is element of installation configuration figure in seventh embodiment of the invention;
Fig. 7 is each component proportion schematic diagram that performance model completes One function in seventh embodiment of the invention;
Fig. 8 is the flow chart of the method for processing data in seventh embodiment of the invention.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should not be by embodiments set forth here
Limited.On the contrary, there is provided these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
In order to solve the following problem of prior art:After the frequency and check figure of CPU reach bottleneck, the meter of CPU is limited to
Calculation ability, cannot further solve the problems, such as system interim card, and user still occurs system during using terminal
Interim card, experiences relatively low;The invention provides a kind of method of processing data, device and terminal, below in conjunction with accompanying drawing and enforcement
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only to explain this
It is bright, do not limit the present invention.
First embodiment of the invention provides a kind of method of processing data, and the flow process of the method is as shown in figure 1, including step
Rapid S102 to S104:
S102, determines that performance indications refer to more than default capabilities in predetermined system running according to default capabilities assessment models
Target is operated.
Said process is when realizing, if predetermined system is the corresponding system of mobile terminal, default capabilities assessment models
It is exactly the model corresponding with entity mobile terminal various pieces, for example, the central processing unit of entity mobile terminal is in default property
Can just there is corresponding funtion part in assessment models.
By default capabilities assessment models come the various situations of simulating mobile terminal normal work, so as to according to the mistake of simulation
Journey to determine predetermined system running in have which operation performance indications more than default capabilities index.
S104, in predetermined system running, corresponding data will be operated to distribute to GPU carries out calculating process, with
Obtain the result of data.
Operation of the performance indications more than default capabilities index is determined in above-mentioned steps S102, then in real predetermined system
During operation, when the operation that finds above-mentioned determination corresponding data, just its corresponding data distribution is carried out to GPU
Calculating is processed.Used as graphic process unit, it is unemployed idling processor when many to GPU, therefore, the present invention is real
Apply example to consider to carry out data calculating by GPU, with offloading the CPU.
The embodiment of the present invention by default capabilities assessment models come simulation system running in various situations, as
According to come determine each operation in performance indications exceed default capabilities index operation, this generic operation is exactly the higher behaviour of load
Make, therefore, it can during running, when the operation is found, just by the corresponding data of the operation distributing
GPU process is given, to share the load of CPU, and then terminal data in use are shared process, will not be occurred again
The situation of system interim card, solves the following problem of prior art:After the frequency and check figure of CPU reach bottleneck, CPU is limited to
Computing capability, cannot further solve the problems, such as system interim card, user still occurs during using terminal
System interim card, experiences relatively low.
Second embodiment of the invention provides a kind of method of processing data, and the flow process of the method is as shown in Fig. 2 including step
Rapid S202 to S206:
S202, determines that performance indications refer to more than default capabilities in predetermined system running according to default capabilities assessment models
Target is operated.
Said process is when realizing, if predetermined system is the corresponding system of mobile terminal, default capabilities assessment models
It is exactly the model corresponding with entity mobile terminal various pieces, for example, the central processing unit of entity mobile terminal is in default property
Can just there is corresponding funtion part in assessment models.
By default capabilities assessment models come the various situations of simulating mobile terminal normal work, so as to according to the mistake of simulation
Journey to determine predetermined system running in have which operation performance indications more than default capabilities index.
S204, by CPU view data is processed data into, and is sent to GPU, so that GPU is counted to view data
Calculation is processed.
Operation of the performance indications more than default capabilities index is determined in above-mentioned steps S202, then in real predetermined system
During operation, when the operation that finds above-mentioned determination corresponding data, CPU is just carried out its corresponding data at camouflage
Reason, will the data disguise as view data.After disguise as view data, it is possible to send the data to GPU, GPU can
To carry out processing to the data.Used as graphic process unit, it is unemployed idling processor when many to GPU,
Therefore, the embodiment of the present invention considers to carry out data calculating by GPU, with offloading the CPU.
S206, by CPU the view data after GPU calculating is processed is received, and carries out dissection process to view data, with
To the result of data.
After the completion of step S204, the view data that GPU has been processed is obtained, this when, CPU can be the figure for having processed
As data is activation to CPU.After CPU receives the view data for having processed, dissection process can be carried out to the view data, so as to
By the view data solution camouflage, original data type is reduced to, to obtain final result.
Third embodiment of the invention provides a kind of method of processing data, the method comprising the steps of S302 to S304:
S302, determines that performance indications refer to more than default capabilities in predetermined system running according to default capabilities assessment models
Target is operated.
Said process is when realizing, if predetermined system is the corresponding system of mobile terminal, default capabilities assessment models
It is exactly the model corresponding with entity mobile terminal various pieces, for example, the central processing unit of entity mobile terminal is in default property
Can just there is corresponding funtion part in assessment models.
By default capabilities assessment models come the various situations of simulating mobile terminal normal work, so as to according to the mistake of simulation
Journey to determine predetermined system running in have which operation performance indications more than default capabilities index.
When implementing, the mode for determining the operation that performance indications exceed default capabilities index in predetermined system can be many
Kind, for example, the number of executions of all operations in predetermined system running is simulated according to default capabilities assessment models, and determination is held
Line number amount exceedes the operation of predetermined number;Or, simulated in predetermined system running according to default capabilities assessment models and owned
The Performance Score of operation, and determine that performance is scored above the operation of default capabilities scoring.
S304, in predetermined system running, corresponding data will be operated to distribute to GPU carries out calculating process, with
Obtain the result of data.
Operation of the performance indications more than default capabilities index is determined in above-mentioned steps S302, then in real predetermined system
During operation, when the operation that finds above-mentioned determination corresponding data, just its corresponding data distribution is carried out to GPU
Calculating is processed.Used as graphic process unit, it is unemployed idling processor when many to GPU, therefore, the present invention is real
Apply example to consider to carry out data calculating by GPU, with offloading the CPU.
Fourth embodiment of the invention provides a kind of method of processing data, and it includes step S402 to S406:
S402, determines that performance indications refer to more than default capabilities in predetermined system running according to default capabilities assessment models
Target is operated.
Said process is when realizing, if predetermined system is the corresponding system of mobile terminal, default capabilities assessment models
It is exactly the model corresponding with entity mobile terminal various pieces, for example, the central processing unit of entity mobile terminal is in default property
Can just there is corresponding funtion part in assessment models.
By default capabilities assessment models come the various situations of simulating mobile terminal normal work, so as to according to the mistake of simulation
Journey to determine predetermined system running in have which operation performance indications more than default capabilities index.
When implementing, the mode for determining the operation that performance indications exceed default capabilities index in predetermined system can be many
Kind, for example, the number of executions of all operations in predetermined system running is simulated according to default capabilities assessment models, and determination is held
Line number amount exceedes the operation of predetermined number;Or, simulated in predetermined system running according to default capabilities assessment models and owned
The Performance Score of operation, and determine that performance is scored above the operation of default capabilities scoring.
S404, by CPU view data is processed data into, and is sent to GPU, so that GPU is counted to view data
Calculation is processed.
Operation of the performance indications more than default capabilities index is determined in above-mentioned steps S402, then in real predetermined system
During operation, when the operation that finds above-mentioned determination corresponding data, CPU is just carried out its corresponding data at camouflage
Reason, will the data disguise as view data.After disguise as view data, it is possible to send the data to GPU, GPU can
To carry out processing to the data.Used as graphic process unit, it is unemployed idling processor when many to GPU,
Therefore, the embodiment of the present invention considers to carry out data calculating by GPU, with offloading the CPU.
S406, by CPU the view data after GPU calculating is processed is received, and carries out dissection process to view data, with
To the result of data.
After the completion of step S404, the view data that GPU has been processed is obtained, this when, CPU can be the figure for having processed
As data is activation to CPU.After CPU receives the view data for having processed, dissection process can be carried out to the view data, so as to
By the view data solution camouflage, original data type is reduced to, to obtain final result.
Fifth embodiment of the invention provides a kind of method of processing data, the method comprising the steps of S502 to S504:
S502, determines that performance indications refer to more than default capabilities in predetermined system running according to default capabilities assessment models
Target is operated.
Said process is when realizing, if predetermined system is the corresponding system of mobile terminal, default capabilities assessment models
It is exactly the model corresponding with entity mobile terminal various pieces, for example, the central processing unit of entity mobile terminal is in default property
Can just there is corresponding funtion part in assessment models.
By default capabilities assessment models come the various situations of simulating mobile terminal normal work, so as to according to the mistake of simulation
Journey to determine predetermined system running in have which operation performance indications more than default capabilities index.
S504, in predetermined system running, corresponding data will be operated to distribute to GPU carries out calculating process, with
Obtain the result of data.
Operation of the performance indications more than default capabilities index is determined in above-mentioned steps S502, then in real predetermined system
During operation, when the operation that finds above-mentioned determination corresponding data, just its corresponding data distribution is carried out to GPU
Calculating is processed.Used as graphic process unit, it is unemployed idling processor when many to GPU, therefore, the present invention is real
Apply example to consider to carry out data calculating by GPU, with offloading the CPU.
During realization, will operation corresponding data when distributing to GPU and being processed, needing to first pass through CPU will wait to locate
The data of reason carry out a camouflage, that is, be processed into view data, and then can send it to GPU, and make GPU to figure
As data carry out calculating process;After GPU is calculated view data and processed, can send to CPU;CPU receives the GPU meters
After view data after calculation process, dissection process is carried out to view data, the view data after process is reduced to into original CPU
The data of needs, to obtain required result.
Performance indications exceed default capabilities index in predetermined system running is determined according to default capabilities assessment models
Operation when, can according to default capabilities assessment models simulate predetermined system running in all operations number of executions, and
Determine that number of executions exceedes the operation of predetermined number;Predetermined system running can also be simulated according to default capabilities assessment models
The Performance Score of middle all operations, and determine that performance is scored above the operation of default capabilities scoring.
If judged according to the number of executions of operation, then when default capabilities assessment models are built, be just not required to
Any setting is carried out to the calculating with regard to Performance Score;If judged according to the Performance Score of operation, then in structure
When building default capabilities assessment models, it is necessary to which the calculating to Performance Score carries out related setting.
No matter which kind of situation, the building process of default capabilities assessment models includes following process:According in predetermined system
Each function of existing carries out Performance Evaluation Model instantiation, and the process is the process for generating each function;For default system
The device parameter of system place equipment builds the Performance Evaluation Model after instantiation, and the process is by each function and entity device
The process for being coupled;The Performance Evaluation Model that all structures are completed is combined, it is corresponding default to obtain predetermined system
Performance Evaluation Model.
If determining which operation needs to give GPU process according to the Performance Score of operation, then according to pre-
If first right for each operation in predetermined system during each function carries out Performance Evaluation Model instantiation present in system
Each function setting component answered, and corresponding service equipment is set for each component;It is correspondence to arrange it for each component again
Service equipment service when Performance Score and weighted value, with according to the Performance Score of each component it is corresponding with weighted value determinations grasp
The Performance Score of work.
Sixth embodiment of the invention provides a kind of device of processing data, and the structural representation of the device is as shown in figure 3, bag
Include:
Determining module 10, for determining that performance indications exceed in predetermined system running according to default capabilities assessment models
The operation of default capabilities index;Processing module 20, couples with determining module 10, in predetermined system running, will grasp
Make corresponding data and distribute to GPU to carry out calculating process, to obtain the result of data.
Wherein, processing module first passes through CPU and processes data into image during processing pending data
Data, and send to GPU, so that GPU carries out calculating process to view data;Again the figure after GPU calculating is processed is received by CPU
As data, and dissection process is carried out to view data, to obtain the result of data.
Determining module specifically for:All operations in predetermined system running are simulated according to default capabilities assessment models
Number of executions, and determine that number of executions exceedes the operation of predetermined number;Or, according to the default system of default capabilities assessment models simulation
The Performance Score of all operations in system running, and determine that performance is scored above the operation of default capabilities scoring.
Said apparatus can also include construction part module, for building default capabilities assessment models.When realizing, module is built
Concrete building process is as follows:Performance Evaluation Model instantiation is carried out according to each function present in predetermined system;For default
The device parameter of system place equipment builds the Performance Evaluation Model after instantiation;By all Performance Evaluation Models for building and completing
It is combined, to obtain the corresponding default capabilities assessment models of predetermined system.
Seventh embodiment of the invention also provides a kind of terminal, it is preferred that the device can be mobile terminal, and it includes above-mentioned
The device of the processing data in sixth embodiment.
During realization, the terminal of the present embodiment can include processor and memory, wherein, memory is used for storage
Construction part module builds in embodiment default capabilities assessment models and related arrange parameter are stated, processor is used to realize above-mentioned determination
The correlation function of module and processing module.Specifically, the processor in the present embodiment can include CPU and GPU, in the present embodiment
Memory can be store program codes any medium.
Alternatively, in the present embodiment, processor performs above-mentioned enforcement according to the program code stored in storage medium
The method and step that example is recorded.Alternatively, the specific example in the present embodiment may be referred to above-described embodiment and optional embodiment
Described in example, the present embodiment will not be described here.Obviously, those skilled in the art should be understood that this above-mentioned
Bright each module or each step can realize that they can be concentrated on single computing device with general computing device,
Or be distributed on the network that multiple computing devices are constituted, they can be with the executable program code of computing device come real
It is existing, it is thus possible to they can also be stored performed by computing device in the storage device, and in some cases, can
To perform shown or described step with the order being different from herein, or they are fabricated to respectively each integrated circuit die
Block, or the multiple modules or step in them are fabricated to single integrated circuit module to realize.So, the present invention is not limited
Combine in any specific hardware and software.
A kind of defect of the fourth embodiment of the invention for mobile phone CPU on calculating task is processed, there is provided processing data
Method solving drawbacks described above, in this embodiment, can be according to the performance model (default capabilities i.e. in above-described embodiment
Assessment models) evaluate and test out CPU process operating system and using when Calculation bottleneck be located, by large-scale cycle calculations task
Distribute to GPU to be calculated, GPU uses the Large-scale parallel computing processors such as pixel coloring device by the calculating of disguise as graphics
Data parallel, is then transferred to CPU by result of calculation, and CPU only serves a control in large-scale cycle calculations task
System and the function of communicating, specific calculating is all given GPU and is completed parallel, it is possible thereby to reduce the time of computation-intensive task
Expense, breaks through the Calculation bottleneck of mobile phone operating system and application, effectively alleviates interim card.
The method that the present embodiment is provided includes when realizing at following 2 points:First point is performance model evaluating mobile phone behaviour
Make system and using when performance, find limit handset capability bottleneck kernel (operating system nucleus), from these kernel
In filter out large-scale cycle calculations task.Second point is that extensive cycle calculations task is placed on GPU at parallel computation
Reason, these calculating tasks may also will carry out one comprising the problems such as Multiple Cycle, beginning and end condition be uncertain to this
The pretreatment of series, and by its disguise as graphics calculating task.
The mobile phone of the method for realizing above-mentioned processing data for providing the present embodiment below is illustrated.
Because processing procedure is including 2 points, therefore, it is corresponding including two modules, i.e. performance measuring and evaluating module (phase in mobile phone
When the partial function of the determining module in above-mentioned sixth embodiment) and parallel computation module (equivalent to above-mentioned sixth embodiment
In processing module partial function).
Performance evaluating module is used to carry out Performance Evaluation to whole mobile phone operating system and application, searches out the whole hand of restriction
The kernel of machine performance, then these kernel are further analyzed, filter out the kernel of the parallel speed-up computations of suitable GPU.And
Row computing module includes pre-processing kernel and Parallel Scheme Design, and pretreatment includes circulation fusion, data camouflage etc..
Because Android phone operating system includes many application programs, so being directed to its particularity, this programme is adopted
The performance model of Component- Based Development.Fig. 4 is the process that the performance model based on android system component maps.
Wherein, the foundation of performance model is divided into three below step:
The first step:The description and instantiation of component performance model (i.e. the corresponding independent model of each function) (gives
The process of each performance model parameter).For example, a model is set up for phone functions, but the parameter of each platform differs
Sample, the process of instantiation is just to confer to the process of each autoregressive parameter of each platform.
The present embodiment describes the performance model of component by including environments parameter that is abstract and quantifying.So, obtain
To be component performance model under specific environment, rather than the component performance model under particular platform.Once set up performance mesh
Mark, it is only necessary to which parameter is instantiated according to specific platform environment, it is possible to which whether the given environment of checking is capable of support member
Performance model.
For each component Ci, it provides n (n>=1) plant service Sj(j=1,2 ... ... n), and the performance of this component is entered
Row description is exactly Perf (Sj(env-par)), wherein Perf represent certain attribute of performance in this programme (the such as response time,
Communication delay etc.), env-par represents ambient parameter.For example, an online component, it can be listened in song software transfer further
Net search song, it is also possible to called by browser interface and then carry out search problem answer.
Second step:Component performance model is set up.The process considers some actual extraneous factors, is added to instantiation
In, obtain mobile phone can performance model.
After the description of component performance model is completed, can be according to some explanation parameters of physical device and current environment
The time required to determine the performance model of structure, such as the delay of network, a database manipulation etc., for an offer n (n>
=1) plant service Sj(j=1,2 ... equipment n).For example, the independent performance model that this builds can with phone functions,
The corresponding component such as function of surfing the Net.
3rd step:Build whole system performance model.The performance model of whole system by each component performance model, each
The performance model of individual equipment and the framework of whole system and design are obtained.
Software performs the basic act that model describes software systems, can be represented with sequence chart.Sequence chart is described
System completes the interaction between component and component needed for certain behavior, and it can be from the Use Case Map of system design and sequential chart
In obtain.Model of element describes each component to the performance model of equipment and related parameter.By software perform model,
The framework of running environment, model of element and system and design can just set up the performance model of whole system.During realization, once
Establish performance objective, it is possible to set up corresponding execution model and model of element, the performance model of whole system also can be by structure
Create, just the performance of software can be estimated accordingly.Execution model, running environment and model of element three are separated
Afterwards, same software systems can be estimated in different environment.The sequential chart of interaction is available such as Fig. 5 institutes between component
Show, the interaction between each component can realize a complete function, for example, it is component to open browser interface, dragnet
Page function is also a component, then to open and will there is interactive relation between two structures of browser and search and webpage.
The attribute of each component is contained in sequential chart, and each equipment is also exist with component form, is coordinated
Configuration figure as shown in Figure 6, it is possible to obtain describing the performance model of whole system.The performance model of whole system such as Fig. 7 institutes
Show.
4th step:System Performance Analysis.
After the performance model of system is set up, it is possible to the performance of system is estimated, it is assumed that certain behavior is public to arrive
N component and k equipment, and at each, etching system is only operated to certain component or equipment, then this behaviour
The performance of work just can be described with following formula:
Perf (Application)=∑ P (Ci)*PerfCi(S(env))+∑P(Mi)*PerfMi(S)
Perf (Application) represents the performance of whole system program, P (C in formulai) represent component CiWeight,
PerfCi(S (env)) represents the performance of the component, P (Mi) represent equipment MiWeight, PerfMiRepresent MiPerformance.For every
One component Ci, its performance can represent with equation below:
PerfCi(S (env))=∑ Psi*PerfCi(Si(env))
The performance for obtaining each component and whole system is estimated after method, can be to each component, system institute
Each for providing services, each action that system is performed carries out Performance Evaluation, in can obtaining whole system running
The bottleneck of restriction whole system is located, then by screening to these bottlenecks, can obtain the parallel speed-up computations of suitable GPU
Module.
Be exactly follow-up parallel computation process after the performance to system is assessed, the process be it is actual should
With process, i.e., to the actual process of data in mobile phone.
Parallel computation is carried out on GPU mainly uses the hardware resources such as the pixel coloring device of GPU, such resource to compare
Although the computing resource computing capability of CPU is weaker, quantity is big, and the processor number for calculating is can be used on general mobile phone GPU
Amount all can be more than 20,000, and carrying out calculating using GPU needs CPU to be communicated and controlled, the flow chart of its calculating process such as Fig. 8
It is shown, including:
Pending data are carried out pretreatment operation by S1, by pending data disguise as graphics data.
S2, by graphics data is activation to GPU.
S3, distributes idle GPU resource and processes graphics data.
S4, according to default paralleling tactic graphics data are calculated.
S5, by result of calculation CPU is back to.
The result of calculation is processed as common data by S6, CPU, and then using the data.
Obviously, those skilled in the art can carry out the essence of various changes and modification without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of method of processing data, it is characterised in that include:
Determine operation of the performance indications more than default capabilities index in predetermined system running according to default capabilities assessment models;
In the predetermined system running, the corresponding data of the operation are distributed to into GPU carries out calculating process, with
To the result of the data.
2. the method for claim 1, it is characterised in that distribute to the operation corresponding data at GPU
Reason, including:
By the data processing it is view data by CPU, and sends to the GPU, so that the GPU is to described image data
Carry out calculating process;
View data after the GPU calculating is processed is received by CPU, and dissection process is carried out to described image data, with
To the result of the data.
3. the method for claim 1, it is characterised in that determine that predetermined system was run according to default capabilities assessment models
Performance indications exceed the operation of default capabilities index in journey, including:
The number of executions of all operations in predetermined system running is simulated according to default capabilities assessment models, and is held described in determining
Line number amount exceedes the operation of predetermined number;Or,
The Performance Score of all operations in predetermined system running is simulated according to default capabilities assessment models, and determines the property
The operation of default capabilities scoring can be scored above.
4. method as claimed any one in claims 1 to 3, it is characterised in that the structure of the default capabilities assessment models
Process, including:
Performance Evaluation Model instantiation is carried out according to each function present in the predetermined system;
The Performance Evaluation Model after instantiation is built for the device parameter of predetermined system place equipment;
The Performance Evaluation Model that all structures are completed is combined, to obtain the corresponding default capabilities of the predetermined system
Assessment models.
5. method as claimed in claim 4, it is characterised in that according to each function progressive present in the predetermined system
Energy assessment models instantiation, including:
For each corresponding each function setting component of operation in the predetermined system, and corresponding service is set for each component
Equipment;
The Performance Score and weighted value when it is corresponding service equipment service is set for each component, with according to each component
The Performance Score and the weighted value determine the Performance Score of respective operations.
6. a kind of device of processing data, it is characterised in that include:
Determining module, for determining that performance indications exceed default property in predetermined system running according to default capabilities assessment models
The operation of energy index;
Processing module, in the predetermined system running, the corresponding data of the operation are distributed to into GPU to be carried out
Calculating is processed, to obtain the result of the data.
7. device as claimed in claim 6, it is characterised in that the processing module specifically for:
By the data processing it is view data by CPU, and sends to the GPU, so that the GPU is to described image data
Carry out calculating process;View data after the GPU calculating is processed is received by CPU, and described image data are parsed
Process, to obtain the result of the data.
8. device as claimed in claim 6, it is characterised in that the determining module specifically for:
The number of executions of all operations in predetermined system running is simulated according to default capabilities assessment models, and is held described in determining
Line number amount exceedes the operation of predetermined number;Or, simulated in predetermined system running according to default capabilities assessment models and owned
The Performance Score of operation, and determine that the Performance Score exceedes the operation of default capabilities scoring.
9. the device as any one of claim 6 to 8, it is characterised in that described device also includes:
Construction part module, for building the default capabilities assessment models, concrete building process is as follows:
Performance Evaluation Model instantiation is carried out according to each function present in the predetermined system;For the predetermined system institute
Performance Evaluation Model after the device parameter of equipment builds instantiation;The Performance Evaluation Model that all structures are completed is carried out into group
Close, to obtain the corresponding default capabilities assessment models of the predetermined system.
10. a kind of terminal, it is characterised in that include:The device of the processing data any one of claim 6 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611215723.9A CN106648895A (en) | 2016-12-26 | 2016-12-26 | Data processing method and device, and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611215723.9A CN106648895A (en) | 2016-12-26 | 2016-12-26 | Data processing method and device, and terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106648895A true CN106648895A (en) | 2017-05-10 |
Family
ID=58827237
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611215723.9A Pending CN106648895A (en) | 2016-12-26 | 2016-12-26 | Data processing method and device, and terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106648895A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108494960A (en) * | 2018-03-21 | 2018-09-04 | 北京小米移动软件有限公司 | Electronic equipment and its control method |
CN109933429A (en) * | 2019-03-05 | 2019-06-25 | 北京达佳互联信息技术有限公司 | Data processing method, device, electronic equipment and storage medium |
CN115134767A (en) * | 2021-03-11 | 2022-09-30 | 上海大唐移动通信设备有限公司 | Method, device and storage medium for improving performance of signaling soft acquisition equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101908035A (en) * | 2010-07-30 | 2010-12-08 | 北京华傲精创科技开发有限公司 | Video coding and decoding method, GPU (Graphics Processing Unit) as well as interacting method and system of same and CPU (Central Processing Unit) |
CN102289782A (en) * | 2010-06-18 | 2011-12-21 | 索尼公司 | Information processing apparatus, and method and program for controlling information processing apparatus |
US8400458B2 (en) * | 2009-09-09 | 2013-03-19 | Hewlett-Packard Development Company, L.P. | Method and system for blocking data on a GPU |
CN103713949A (en) * | 2012-10-09 | 2014-04-09 | 鸿富锦精密工业(深圳)有限公司 | System and method for dynamic task allocation |
CN104484234A (en) * | 2014-11-21 | 2015-04-01 | 中国电力科学研究院 | Multi-front load flow calculation method and system based on GPU (graphics processing unit) |
-
2016
- 2016-12-26 CN CN201611215723.9A patent/CN106648895A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8400458B2 (en) * | 2009-09-09 | 2013-03-19 | Hewlett-Packard Development Company, L.P. | Method and system for blocking data on a GPU |
CN102289782A (en) * | 2010-06-18 | 2011-12-21 | 索尼公司 | Information processing apparatus, and method and program for controlling information processing apparatus |
CN101908035A (en) * | 2010-07-30 | 2010-12-08 | 北京华傲精创科技开发有限公司 | Video coding and decoding method, GPU (Graphics Processing Unit) as well as interacting method and system of same and CPU (Central Processing Unit) |
CN103713949A (en) * | 2012-10-09 | 2014-04-09 | 鸿富锦精密工业(深圳)有限公司 | System and method for dynamic task allocation |
CN104484234A (en) * | 2014-11-21 | 2015-04-01 | 中国电力科学研究院 | Multi-front load flow calculation method and system based on GPU (graphics processing unit) |
Non-Patent Citations (1)
Title |
---|
刘晓明,等: "基于模型的构件系统性能预测综述", 《系统仿真学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108494960A (en) * | 2018-03-21 | 2018-09-04 | 北京小米移动软件有限公司 | Electronic equipment and its control method |
CN109933429A (en) * | 2019-03-05 | 2019-06-25 | 北京达佳互联信息技术有限公司 | Data processing method, device, electronic equipment and storage medium |
CN115134767A (en) * | 2021-03-11 | 2022-09-30 | 上海大唐移动通信设备有限公司 | Method, device and storage medium for improving performance of signaling soft acquisition equipment |
CN115134767B (en) * | 2021-03-11 | 2024-02-09 | 上海大唐移动通信设备有限公司 | Method, device and storage medium for improving performance of signaling soft acquisition equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109460348B (en) | Pressure measurement method and device of game server | |
CN106502889B (en) | The method and apparatus for predicting cloud software performance | |
Ankenman et al. | A quick assessment of input uncertainty | |
CN106803799B (en) | Performance test method and device | |
CN108052979A (en) | The method, apparatus and equipment merged to model predication value | |
CN108960629A (en) | Distribution method, device and the computer readable storage medium of maintenance task | |
CN106502890A (en) | Method for generating test case and system | |
CN106648895A (en) | Data processing method and device, and terminal | |
CN107967204A (en) | Line pushes method, system and the terminal device surveyed | |
CN114095567B (en) | Data access request processing method and device, computer equipment and medium | |
CN108052444A (en) | A kind of method and apparatus of performance test for mobile application | |
CN107807935B (en) | Using recommended method and device | |
US20220284374A1 (en) | Skills gap management platform | |
CN110750928A (en) | Finite element model optimization method and device and electronic equipment | |
CN107197120B (en) | Image source compatibility test method and system | |
CN107220169B (en) | Method and equipment for simulating server to return customized data | |
CN114564374A (en) | Operator performance evaluation method and device, electronic equipment and storage medium | |
CN109087124A (en) | A kind of application program Value Prediction Methods and device | |
CN114785693B (en) | Virtual network function migration method and device based on layered reinforcement learning | |
CN117033760A (en) | Object recommendation method, device, equipment, storage medium and program product | |
CN112632885B (en) | Software and hardware combined verification system and method | |
CN113742187A (en) | Capacity prediction method, device, equipment and storage medium of application system | |
CN112242959B (en) | Micro-service current-limiting control method, device, equipment and computer storage medium | |
CN108052378A (en) | The method for scheduling task for the profit sensitivity applied towards complex simulation workflow | |
CN110069395B (en) | Method and device for simulating asynchronous interface, storage medium and computer equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |
|
RJ01 | Rejection of invention patent application after publication |